python机器学习（分类）

import numpy as np
import pandas as pd
df = pd.read_csv('hw.csv')
df.dropna()
df.drop_duplicates()
from sklearn.preprocessing import LabelEncoder
df['Gender'] = LabelEncoder().fit_transform(df['Gender'])
print(df)
X = df[['Height','Weight']]
Y = df[['Gender']]
from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,train_size=0.8)

# 数据建模
# 逻辑回归
from sklearn.linear_model import LogisticRegression
# 逻辑回归类创建对象
# model = LogisticRegression()
# 朴素贝叶斯
# from sklearn.naive_bayes import MultinomialNB
# model = MultinomialNB()
# 决策树
# from sklearn.tree import DecisionTreeClassifier
# model = DecisionTreeClassifier()
# 支持向量机
from sklearn.svm import SVC
model = SVC()
model.fit(X_train,Y_train)
print(model.score(X_test,Y_test))
print(model.predict([[165,58]]))

import matplotlib.pyplot as plt
h = np.arange(150,200,0.1)
w = np.arange(30,90,0.1)
newh,neww = np.meshgrid(h,w)
plt.pcolormesh(newh,neww,model.predict(np.c_[newh.ravel(),neww.ravel()]).reshape(newh.shape))
plt.scatter(df['Height'],df['Weight'],c=df['Gender'])
plt.show()

hw.csv数据：

Gender,Age,Height,Weight
M,21,163,60
M,22,164,56
M,21,165,60
M,23,168,55
M,21,169,60
M,21,170,54
M,23,170,80
M,23,170,64
M,22,171,67
M,22,172,65
M,23,172,60
M,21,172,60
M,23,173,60
M,22,173,62
M,21,174,65
M,22,175,70
M,22,175,70
M,22,175,65
M,23,175,60
M,21,175,62
M,21,176,58
M,21,178,70
M,23,178,75
M,23,180,63
M,23,180,71
M,23,183,75
F,20,153,42
F,20,156,44
F,21,156,38
F,21,157,48
F,21,158,52
F,23,158,45
F,22,159,43
F,22,160,50
F,21,160,45
F,21,160,52
F,23,160,50
F,22,161,50
F,21,161,45
F,21,162,55
F,20,162,60
F,20,163,56
F,20,163,56
F,21,163,59
F,22,164,55
F,23,164,47
F,21,165,45
F,21,165,45
F,20,165,60
F,20,168,58
F,21,168,49